Papers
See AI2's Award Winning Papers
Learn more about AI2's Lasting Impact Award
Viewing 91-100 of 106 papers
Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generation
Amit Mor-Yosef, Ido Dagan, Yoav GoldbergNAACL • 2019 Data-to-text generation can be conceptually divided into two parts: ordering and structuring the information (planning), and generating fluent language describing the information (realization). Modern neural generation systems conflate these two steps into a…Studying the Inductive Biases of RNNs with Synthetic Variations of Natural Languages
Shauli Ravfogel, Yoav Goldberg, Tal LinzenNAACL • 2019 How do typological properties such as word order and morphological case marking affect the ability of neural sequence models to acquire the syntax of a language? Cross-linguistic comparisons of RNNs' syntactic performance (e.g., on subject-verb agreement…Value-based Search in Execution Space for Mapping Instructions to Programs
Dor Muhlgay, Jonathan Herzig, Jonathan BerantNAACL • 2019 Training models to map natural language instructions to programs given target world supervision only requires searching for good programs at training time. Search is commonly done using beam search in the space of partial programs or program trees, but as the…White-to-Black: Efficient Distillation of Black-Box Adversarial Attacks
Or Gorodissky, Yoav Chai, Yotam Gil, Jonathan BerantNAACL • 2019 We show that a neural network can learn to imitate the optimization process performed by white-box attack in a much more efficient manner. We train a black-box attack through this imitation process and show our attack is 19x-39x faster than the white-box…Neural network gradient-based learning of black-box function interfaces
Alon Jacovi, Guy Hadash, Einat Kermany, Boaz Carmeli, Ofer Lavi, George Kour, Jonathan BerantICLR • 2019 Deep neural networks work well at approximating complicated functions when provided with data and trained by gradient descent methods. At the same time, there is a vast amount of existing functions that programmatically solve different tasks in a precise…Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction
Roei Herzig, Moshiko Raboh, Gal Chechik, Jonathan Berant, Amir GlobersonNeurIPS • 2018 Machine understanding of complex images is a key goal of artificial intelligence. One challenge underlying this task is that visual scenes contain multiple inter-related objects, and that global context plays an important role in interpreting the scene. A…Memory Augmented Policy Optimization for Program Synthesis and Semantic Parsing
Chen Liang, Mohammad Norouzi, Jonathan Berant, Quoc Le, Ni LaoNeurIPS • 2018 This paper presents Memory Augmented Policy Optimization (MAPO): a novel policy optimization formulation that incorporates a memory buffer of promising trajectories to reduce the variance of policy gradient estimates for deterministic environments with…Adversarial Removal of Demographic Attributes from Text Data
Yanai Elazar, Yoav GoldbergEMNLP • 2018 Recent advances in Representation Learning and Adversarial Training seem to succeed in removing unwanted features from the learned representation. We show that demographic information of authors is encoded in—and can be recovered from—the intermediate…Can LSTM Learn to Capture Agreement? The Case of Basque
Shauli Ravfogel, Francis M. Tyers, Yoav GoldbergEMNLP • Workshop: Analyzing and interpreting neural networks for NLP • 2018 Sequential neural networks models are powerful tools in a variety of Natural Language Processing (NLP) tasks. The sequential nature of these models raises the questions: to what extent can these models implicitly learn hierarchical structures typical to human…Decoupling Structure and Lexicon for Zero-Shot Semantic Parsing
Jonathan Herzig, Jonathan BerantEMNLP • 2018 Building a semantic parser quickly in a new domain is a fundamental challenge for conversational interfaces, as current semantic parsers require expensive supervision and lack the ability to generalize to new domains. In this paper, we introduce a zero-shot…